Improved EEMD-based crude oil price forecasting using LSTM networks

#artificialintelligence

The inadequacy of traditional forecasting model based on EEMD in practical work. For WTI, the first four IMFs decomposed by EEMD are suitable as inputs. Considering the actual demand of crude oil price forecasting, a novel model based on ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM) is proposed. In practical work, the model trained by historical data will be used in later data. Then the forecasting models based on EEMD need re-execute EEMD to update decomposition results of price series after getting new data.


Beyond One-Step-Ahead Forecasting: Evaluation of Alternative Multi-Step-Ahead Forecasting Models for Crude Oil Prices

arXiv.org Artificial Intelligence

An accurate prediction of crude oil prices over long future horizons is challenging and of great interest to governments, enterprises, and investors. This paper proposes a revised hybrid model built upon empirical mode decomposition (EMD) based on the feed-forward neural network (FNN) modeling framework incorporating the slope-based method (SBM), which is capable of capturing the complex dynamic of crude oil prices. Three commonly used multi-step-ahead prediction strategies proposed in the literature, including iterated strategy, direct strategy, and MIMO (multiple-input multiple-output) strategy, are examined and compared, and practical considerations for the selection of a prediction strategy for multi-step-ahead forecasting relating to crude oil prices are identified. The weekly data from the WTI (West Texas Intermediate) crude oil spot price are used to compare the performance of the alternative models under the EMD-SBM-FNN modeling framework with selected counterparts. The quantitative and comprehensive assessments are performed on the basis of prediction accuracy and computational cost. The results obtained in this study indicate that the proposed EMD-SBM-FNN model using the MIMO strategy is the best in terms of prediction accuracy with accredited computational load.


Crude Oil Price Update: Venezuela, Iran Worries Lead WTI Back Over $70

International Business Times

For the first time since November 2014, the price of WTI crude went beyond $70 a barrel, trading at a high of $70.59 at 11:10 p.m. EDT Sunday. The U.S. benchmark trails the global Brent crude price, which had breached the $70-level briefly in January, and has stayed above that mark consistently since the second week of April. Since its low point in mid-January 2016, the price of crude oil has made a sustained recovery, but fresh concerns over Venezuela and the future of the nuclear deal with Iran could pare back the gains. And one of the factors for the WTI crude price being lower than Brent is the domestic shale production, which has been booming. The political situation in Venezuela, partially arising from and contributing to the economic crisis gripping the country, has meant the South American country has been unable to invest in its petrochemicals industry, and its output has fallen to about 1.5 million barrels a day, half its peak in the 2000s.


Crude Oil Prices Today

#artificialintelligence

Despite numerous bankruptcies in the U.S. shale industry, producers are showing profits and increasing rig counts amid OPEC's production cuts


Japan's wholesale prices fell 4.2% in June

The Japan Times

Wholesale prices fell 4.2 percent in June from a year earlier for a 15th straight month of decline, impacted by falling crude oil and commodity prices, as well as a strong yen, Bank of Japan data showed Tuesday. The index of corporate goods prices stood at 99.2 against the 2010 base of 100, the central bank said in a preliminary report. On a month-on-month basis, the index edged down 0.1 percent, after rising for the first time in a year in May, due apparently to the negative impact of the yen's sharp rise, particularly against the dollar. As wholesale prices often affect consumer prices, the latest data underpinned the difficulty the BOJ faces in pursuing its 2 percent inflation target. Prices of petroleum and coal products plunged 21.0 percent from a year earlier, and those of nonferrous metals slid 17.6 percent, reflecting softness in commodity markets.